Why augmentation multiplies training data in Computer Vision - Quick Recap

Recall & Review

beginner

What is data augmentation in computer vision?

Data augmentation is a technique that creates new training images by applying simple changes like rotation, flipping, or color shifts to existing images. This helps the model learn better by seeing more varied examples.

beginner

Why does augmentation multiply the amount of training data?

Because each original image can be changed in many ways, augmentation creates many new images from one. This increases the total number of training examples, helping the model learn more patterns.

intermediate

How does augmentation help prevent overfitting?

By showing the model many different versions of images, augmentation stops the model from memorizing exact images. Instead, the model learns general features that work well on new, unseen images.

beginner

Name three common augmentation techniques used in computer vision.

Common techniques include flipping images horizontally, rotating images by small angles, and changing brightness or colors slightly.

beginner

What is the main benefit of multiplying training data with augmentation?

The main benefit is that the model gets more diverse examples to learn from, which improves its ability to recognize objects in different situations and reduces errors on new images.

What does data augmentation do to training images?

A Deletes half of the images to reduce size

B Creates new images by modifying existing ones

C Converts images to black and white only

D Copies images without any changes

Data augmentation creates new images by applying changes like rotation or flipping to existing images.

Why is multiplying training data helpful for a model?

A It helps the model learn more varied examples

B It makes the model run faster

C It reduces the number of classes

D It removes noise from images

More varied examples help the model learn better and generalize to new data.

Which of these is NOT a common augmentation technique?

A Adding random noise to labels

B Rotating images slightly

C Flipping images horizontally

D Changing image brightness

Adding noise to labels is not an image augmentation technique.

How does augmentation reduce overfitting?

A By removing hard examples from training

B By decreasing the number of training images

C By simplifying the model architecture

D By increasing data variety so the model doesn't memorize exact images

Augmentation increases variety, helping the model learn general features instead of memorizing.

If you have 100 images and apply 3 different augmentations, how many images do you have for training?

A 100

B 300

C 400

D 600

Original 100 images plus 3 augmentations each (3 x 100 = 300) equals 400 images total.

Explain in your own words why data augmentation multiplies training data in computer vision.

Think about how one photo can become many different photos by small changes.

Describe how multiplying training data with augmentation helps reduce overfitting.

Consider why seeing many versions of the same object helps the model.